2.7K skills · sorted by relevance
Reproduce Mastra Code bugs with a real model and compare timestamped logs across network, streaming, execution, and terminal interface layers. Use the evidence to locate timing problems, incorrect token rates, flicker, or stuck status displays.
Test mastracode’s terminal interface in Konsole, covering model setup, conversation switching, task state isolation, and display issues. The guide combines interactive checks with scripted rendering tests and troubleshooting steps for common build and configuration problems.
Reproduce chat errors, retries, parallel tool calls, and app creation in a running desktop application. Check how messages and cards appear, including interrupted replies, grouped steps, and error details.
Turn method notes or figure descriptions into academic architecture and concept illustrations. Claude plans and reviews the layout, while a local Codex bridge generates images, with refinement rounds and final PNG, LaTeX snippet, and review records.
Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.
Write or modernize C++ with guidance on C++20, C++23, and C++26 features. Review memory ownership, error handling, and template constraints, with recommendations for compiler protections and runtime checks that detect bugs.
Create and configure Claude Code agents using Markdown files with YAML configuration headers. Define when each agent should run, write its responsibilities and workflow, choose models and tools, and check configuration and triggering behavior.
Investigate unexpected Claude Code output by matching a session’s local transcript with production router logs. Identify the serving model and trace response conversion code to explain empty blocks, tool output, or other rendering symptoms.
Upgrade the chat app’s fast or good model slot across Rust backend code and the frontend. Updates model definitions, selection logic, generated types, and display names, then checks compilation and consistency.
Create and configure Claude Code agents using Markdown files with YAML configuration headers. Define when each agent should run, write its responsibilities and workflow, choose models and tools, and check configuration and triggering behavior.
Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.
Generate images, reference-based edits, and video clips from stills through configured APIs or local Codex and Grok tools. Check available generation options, configure keys, track estimated costs, and resume interrupted jobs.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
The English summary is being prepared. Showing the original description.
Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: assesses the codebase, rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Also has an access-only mode for checking or enabling Bedrock model access for specific models (e.g. 'request access to Claude on Bedrock', 'which models do I turn on') with no code migration — it checks each model and walks the right access step, then stops. Not for agent runtime selection or agent migration planning (use agent-advisor), nor standalone cost estimates or infra-only migration. The full migration REQUIRES gcp-to-aws OR azure-to-aws installed alongside this skill (gcp-to-aws preferred when both are present); access-only mode needs neither.
The English summary is being prepared. Showing the original description.
Generate a complete, beginner-friendly explanation of an entire code repository as a set of markdown files. Maps the repo structure with `treecap` (installing it if missing), studies the actual source, then writes a `CODE_EXPLANATION/` folder containing an `OVERVIEW.md` plus numbered deep-dive files (01_architecture.md, 02_models.md, ...) that explain how the code is built, what it does, and how the pieces fit together — illustrated with real code excerpts. Use this skill whenever the user wants to understand, document, onboard onto, or get a walkthrough of a codebase: phrases like "explain this repo", "explain the code", "code explanation", "walk me through this codebase", "help me understand how this is built", "document the architecture", or "what does this project do" — even if they don't say the word "skill". Prefer this over ad-hoc summaries whenever the goal is a durable, written explanation of a whole repo.
The English summary is being prepared. Showing the original description.
Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or imported models rebuilt as dlnetwork for lean hardware, (2) direct C/C++ code generation from PyTorch and LiteRT models. Both patterns support all targets (Cortex-M/A/R, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, loadLiteRTModel, importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromTensorFlow, importNetworkFromKeras, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.
The English summary is being prepared. Showing the original description.
Migrate, modernize, and upgrade codebases to AWS. Run analysis on repos for tech debt, security vulnerabilities, and modernization opportunities. Transforms .NET Framework to .NET 8/10, mainframe COBOL to Java, VMware VMs to EC2, SQL Server to Aurora, and upgrades Java/Python/Node.js versions and AWS SDKs. Use when the user says "migrate .NET to AWS", "upgrade Java to 17/21", "modernize COBOL", "modernize mainframe", "move VMware to EC2", "convert SQL Server to Aurora", "upgrade Python version", "migrate AWS SDK", "transform this codebase", "analyze for issues", "find tech debt", "what tech debt", "security vulnerabilities", "CVEs", "what's wrong with my code", "assess my repos", "where do I start", "find what's outdated", "analyze my repos", "AWS Transform - continuous modernization", "continuous modernization" or "continuous-modernization". Don't use for infrastructure provisioning, CI/CD pipelines, or general coding tasks.
The English summary is being prepared. Showing the original description.
Use when you need to refactor Java code to adopt modern Java features (Java 8+) — including migrating anonymous classes to lambdas, replacing Iterator loops with Stream API, adopting Optional for null safety, switching from legacy Date/Calendar to java.time, using collection factory methods, applying text blocks, var inference, or leveraging Java 25 features like flexible constructor bodies and module import declarations. This should trigger for requests such as Review Java code for modern Java development; Apply best practices for modern Java development in Java code; Modernize Java code with records pattern matching or switch expressions; Replace legacy idioms with modern Java features; Adopt Java 8+ language features safely. Part of Plinth Toolkit
The English summary is being prepared. Showing the original description.
Automatically extract abstract finite-state models in SMV/NuSMV format from source code (C/C++, Java, Python) for formal model checking. Use when users need to: (1) Generate SMV models from program code for verification, (2) Extract state-transition models from protocol implementations, (3) Analyze control flow and data flow to construct formal models, (4) Create models for checking safety and liveness properties, (5) Convert imperative code to declarative state machines. Particularly effective for protocol implementations, concurrent systems, and control logic with clear state transitions.
The English summary is being prepared. Showing the original description.
Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, exposing the orchestrator's 69 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose, or running as an Agent Client Protocol (ACP) agent that Zed / JetBrains / Neovim / Emacs / VS Code / dsh can drive directly. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol", "ultracode", "dynamic workflow", "fanout", "fan-out", "best-of-N", "steer turn", "interrupt turn", "fork thread", "rollback turns", "acp", "agent client protocol", "clawo acp", "zed agent", "jetbrains agent", "external agent", "dsh subagent", "deepseek harness".
The English summary is being prepared. Showing the original description.
Figma 转 Photoshop (PSD) (Figma → Photoshop (PSD) 设计稿转换 (从业者视角) — 把 Figma 设计文件高保真转换为 Photoshop 分层 PSD, 核心是对齐两个工具的概念/渲染差异, 让产出的设计稿视觉一致. 覆盖: (a) 概念映射 — Figma frame / auto-layout / component / variant / constraint / vector-network / boolean / effect (drop·inner shadow / layer·background blur) / mask / blend mode / gradient / text-engine / color 与 Photoshop artboard / group / smart-object / linked / layer-style / shape-layer / path / clipping·layer mask / blend-mode 的对应关系与不可逆损耗点; (b) 转换方法栈 — 插件直出 PSD / 导出图层 (PNG·SVG) 再重组 / SVG·PDF 桥接 / 手工重建 / Figma REST API + Photoshop UXP·ExtendScript 脚本化, 各法在保真度-可编辑性-工时上的权衡与选型; (c) 保真度 QA — 字体回退与缺字处理 / 颜色空间 (sRGB·ICC profile) / 效果参数对齐 / @Nx·DPI 与栅格化 / 像素 diff 验收; (d) 两种交付目标 — 可编辑分层 PSD vs 像素保真扁平 PSD 的方法选择. 主战场 = Figma Community 插件 + Adobe 官方文档/论坛 + 设计交付 (design handoff) 实践 + 设计师社区. 不含: PSD→Figma 反向转换 / Sketch / Adobe XD / 纯前端 code handoff (HTML·CSS) / 印刷 CMYK 专业制版 (仅触及).) Master OS — automated mastery of Figma → Photoshop (PSD) 设计稿转换 (从业者视角) — 把 Figma 设计文件高保真转换为 Photoshop 分层 PSD, 核心是对齐两个工具的概念/渲染差异, 让产出的设计稿视觉一致. 覆盖: (a) 概念映射 — Figma frame / auto-layout / component / variant / constraint / vector-network / boolean / effect (drop·inner shadow / layer·background blur) / mask / blend mode / gradient / text-engine / color 与 Photoshop artboard / group / smart-object / linked / layer-style / shape-layer / path / clipping·layer mask / blend-mode 的对应关系与不可逆损耗点; (b) 转换方法栈 — 插件直出 PSD / 导出图层 (PNG·SVG) 再重组 / SVG·PDF 桥接 / 手工重建 / Figma REST API + Photoshop UXP·ExtendScript 脚本化, 各法在保真度-可编辑性-工时上的权衡与选型; (c) 保真度 QA — 字体回退与缺字处理 / 颜色空间 (sRGB·ICC profile) / 效果参数对齐 / @Nx·DPI 与栅格化 / 像素 diff 验收; (d) 两种交付目标 — 可编辑分层 PSD vs 像素保真扁平 PSD 的方法选择. 主战场 = Figma Community 插件 + Adobe 官方文档/论坛 + 设计交付 (design handoff) 实践 + 设计师社区. 不含: PSD→Figma 反向转换 / Sketch / Adobe XD / 纯前端 code handoff (HTML·CSS) / 印刷 CMYK 专业制版 (仅触及).: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on Figma → Photoshop (PSD) 设计稿转换 (从业者视角) — 把 Figma 设计文件高保真转换为 Photoshop 分层 PSD, 核心是对齐两个工具的概念/渲染差异, 让产出的设计稿视觉一致. 覆盖: (a) 概念映射 — Figma frame / auto-layout / component / variant / constraint / vector-network / boolean / effect (drop·inner shadow / layer·background blur) / mask / blend mode / gradient / text-engine / color 与 Photoshop artboard / group / smart-object / linked / layer-style / shape-layer / path / clipping·layer mask / blend-mode 的对应关系与不可逆损耗点; (b) 转换方法栈 — 插件直出 PSD / 导出图层 (PNG·SVG) 再重组 / SVG·PDF 桥接 / 手工重建 / Figma REST API + Photoshop UXP·ExtendScript 脚本化, 各法在保真度-可编辑性-工时上的权衡与选型; (c) 保真度 QA — 字体回退与缺字处理 / 颜色空间 (sRGB·ICC profile) / 效果参数对齐 / @Nx·DPI 与栅格化 / 像素 diff 验收; (d) 两种交付目标 — 可编辑分层 PSD vs 像素保真扁平 PSD 的方法选择. 主战场 = Figma Community 插件 + Adobe 官方文档/论坛 + 设计交付 (design handoff) 实践 + 设计师社区. 不含: PSD→Figma 反向转换 / Sketch / Adobe XD / 纯前端 code handoff (HTML·CSS) / 印刷 CMYK 专业制版 (仅触及). problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「figma 转 psd」「figma to psd」「figma 转 photoshop」「figma 导出 psd」「设计稿转换」
The English summary is being prepared. Showing the original description.
Runs several language models as independent coders on the same labeling or discovery task and reads their disagreement as data — panel assembly for model diversity, keeping votes independent, consensus rules, agreement statistics (Cohen's and Fleiss kappa, Krippendorff's alpha), the correlated-errors caveat that stops agreement being mistaken for validity, human validation beyond the panel, and reporting. Use when the user asks about a council, panel, ensemble, or jury of models, asks how to combine several models' labels, or asks what kappa or alpha to report for model coders. Single-model codebook and validation work goes to text-classification, per-item confidence to llm-calibration-logprobs.
The English summary is being prepared. Showing the original description.
SwiftUI のレイアウト落とし穴・ベストプラクティス・非推奨パターンと、 iOS / watchOS アプリの実機配布 (Provisioning / App Group / Code Signing / Apple Watch Developer Mode / Xcode 15+ Debug dylib) トラブルシューティング のガイド。コード生成・修正時に既知のレイアウトバグを防ぎ、 App Group + watchOS + Apple Watch の実機インストール失敗を 7 段階フレームワークで診断・解消する。 Use when: SwiftUI のコードを書く・修正するとき。 レイアウト崩れを修正するとき。safeAreaInset や ViewThatFits を使うとき。 マルチデバイス対応するとき。iOS + watchOS アプリの実機ビルド / 配布で provisioning / App Group / Manual Signing / Apple Watch の UDID / Xcode 自動署名の 罠に詰まったとき。Apple Watch に "Could not install at this time" が出たとき。 Triggers: "SwiftUI", "layout", "safeAreaInset", "ViewThatFits", "GeometryReader", "レイアウト", "崩れ", "表示バグ", "iPhone SE", "ATT", "ATTrackingManager", "requestTrackingAuthorization", "AdMob", "広告", "Provisioning Profile", "App Group", "Manual Signing", "Code Signing", "Apple Watch", "watchOS", "Install できない", "Could not install at this time", "Bundle ID 紐付け", "Xcode Automatic Signing", "embedded.mobileprovision", "Spaceship", "App Store Connect API", "WKCompanionAppBundleIdentifier", "Developer Mode", "Privacy & Security", "watchOS Developer Mode", "Apple Watch に App を入れられない", "整合性を確認できなかった", "integrity check", "ENABLE_DEBUG_DYLIB", "__preview.dylib", "debug.dylib", "Xcode 15 Preview", "SwiftUI Preview dylib", "ENABLE_PREVIEWS", "AppIntents", "AppShortcut", "AppShortcutsProvider", "AppEntity", "AppEnum", "Siri", "Siri に流れる", "Siri がリマインダーに流れる", "updateAppShortcutParameters", "Invalid parameter type", "Invalid Utterance", "applicationName", "CFBundleDisplayName", "CFBundleSpokenName", "TaskEntityQuery", "AppEntityQuery", "TimelineProvider", "recommendations", "WatchConnectivity", "WCSession", "updateApplicationContext", "sessionDidBecomeInactive", "iPhone と Watch でデータ共有", "App Group 共有できない", "scenePhase", "ポーリング", "watchOS バッテリー", "TextField 文字色 watchOS", "Picker 文字色 watchOS", "Single Size AppIcon", "watchOS AppIcon"
The English summary is being prepared. Showing the original description.
Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, customization, /simplify for code quality, /batch for parallel code migrations, /loop for scheduled tasks, code review agents, /btw for mid-task questions, /effort max reasoning, remote control sessions, voice mode, setup scripts, session naming, /color, PostCompact hook, auto mode, /schedule cloud jobs, iMessage plugin, auto-memory, and auto-dream, mobile app, session teleporting, Cowork Dispatch, Chrome extension, Desktop app, /branch forking, --bare SDK startup, --add-dir multi-repo, --agent custom agents, /voice input.
The English summary is being prepared. Showing the original description.